We present a novel approach to parse web search queries for the purpose of automatic tagging of the queries. We will define a set of probabilistic context-free rules, which genera...
Cognitive Agents must be able to decide their actions based on their recognized states. In general, learning mechanisms are equipped for such agents in order to realize intellgent ...
In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits m...
Maximum likelihood estimators are often of limited practical use due to the intensive computation they require. We propose a family of alternative estimators that maximize a stoch...
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
Samuel Thomas, Patrick Nguyen, Geoffrey Zweig, Hyn...